Training in progress, step 200, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 69527352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0523d76765ca4cd622289ee0640efa6aa34e1774dea35dcf0070831154c6fff3
|
| 3 |
size 69527352
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 35778452
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76a57303386d0d82dc7b0f192d8d47fdae4b04fea3235f5fd0e62f279fb19f6c
|
| 3 |
size 35778452
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:423d2bed4877a4fee141ad61c043eb42a11b4a716dd9a654808bedc70a2ada74
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a27b052646dcb561cbd68156c30bd466ce59bda64cf3c8eba9c3c1113af9827c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1089,6 +1089,364 @@
|
|
| 1089 |
"eval_samples_per_second": 65.491,
|
| 1090 |
"eval_steps_per_second": 16.377,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1112,12 +1470,12 @@
|
|
| 1112 |
"should_evaluate": false,
|
| 1113 |
"should_log": false,
|
| 1114 |
"should_save": true,
|
| 1115 |
-
"should_training_stop":
|
| 1116 |
},
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
-
"total_flos":
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8490656018257141,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.18912529550827423,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1089 |
"eval_samples_per_second": 65.491,
|
| 1090 |
"eval_steps_per_second": 16.377,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.14278959810874706,
|
| 1095 |
+
"grad_norm": 0.45450514554977417,
|
| 1096 |
+
"learning_rate": 4.995066821070679e-05,
|
| 1097 |
+
"loss": 0.1451,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.14373522458628843,
|
| 1102 |
+
"grad_norm": 0.5641042590141296,
|
| 1103 |
+
"learning_rate": 4.980286753286195e-05,
|
| 1104 |
+
"loss": 0.19,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.14468085106382977,
|
| 1109 |
+
"grad_norm": 0.6517515182495117,
|
| 1110 |
+
"learning_rate": 4.9557181268217227e-05,
|
| 1111 |
+
"loss": 0.2196,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.14562647754137115,
|
| 1116 |
+
"grad_norm": 0.5124554634094238,
|
| 1117 |
+
"learning_rate": 4.9214579028215776e-05,
|
| 1118 |
+
"loss": 0.2285,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.14657210401891252,
|
| 1123 |
+
"grad_norm": 0.4333844482898712,
|
| 1124 |
+
"learning_rate": 4.877641290737884e-05,
|
| 1125 |
+
"loss": 0.2272,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.1475177304964539,
|
| 1130 |
+
"grad_norm": 0.3877612352371216,
|
| 1131 |
+
"learning_rate": 4.8244412147206284e-05,
|
| 1132 |
+
"loss": 0.3144,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.14846335697399526,
|
| 1137 |
+
"grad_norm": 0.3211458921432495,
|
| 1138 |
+
"learning_rate": 4.762067631165049e-05,
|
| 1139 |
+
"loss": 0.3578,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.14940898345153664,
|
| 1144 |
+
"grad_norm": 0.24879109859466553,
|
| 1145 |
+
"learning_rate": 4.690766700109659e-05,
|
| 1146 |
+
"loss": 0.2756,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.150354609929078,
|
| 1151 |
+
"grad_norm": 0.22662314772605896,
|
| 1152 |
+
"learning_rate": 4.610819813755038e-05,
|
| 1153 |
+
"loss": 0.2839,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.15130023640661938,
|
| 1158 |
+
"grad_norm": 0.23902210593223572,
|
| 1159 |
+
"learning_rate": 4.522542485937369e-05,
|
| 1160 |
+
"loss": 0.3703,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.15224586288416075,
|
| 1165 |
+
"grad_norm": 0.23963478207588196,
|
| 1166 |
+
"learning_rate": 4.426283106939474e-05,
|
| 1167 |
+
"loss": 0.3972,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.15319148936170213,
|
| 1172 |
+
"grad_norm": 0.23576639592647552,
|
| 1173 |
+
"learning_rate": 4.3224215685535294e-05,
|
| 1174 |
+
"loss": 0.3027,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.1541371158392435,
|
| 1179 |
+
"grad_norm": 0.33861732482910156,
|
| 1180 |
+
"learning_rate": 4.211367764821722e-05,
|
| 1181 |
+
"loss": 0.481,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.15508274231678487,
|
| 1186 |
+
"grad_norm": 0.34786704182624817,
|
| 1187 |
+
"learning_rate": 4.093559974371725e-05,
|
| 1188 |
+
"loss": 0.441,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.15602836879432624,
|
| 1193 |
+
"grad_norm": 0.5184177160263062,
|
| 1194 |
+
"learning_rate": 3.969463130731183e-05,
|
| 1195 |
+
"loss": 0.5629,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.15697399527186762,
|
| 1200 |
+
"grad_norm": 0.38847318291664124,
|
| 1201 |
+
"learning_rate": 3.8395669874474915e-05,
|
| 1202 |
+
"loss": 0.5856,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.157919621749409,
|
| 1207 |
+
"grad_norm": 0.4933064877986908,
|
| 1208 |
+
"learning_rate": 3.704384185254288e-05,
|
| 1209 |
+
"loss": 0.6682,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.15886524822695036,
|
| 1214 |
+
"grad_norm": 0.4688006043434143,
|
| 1215 |
+
"learning_rate": 3.564448228912682e-05,
|
| 1216 |
+
"loss": 0.6222,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.15981087470449173,
|
| 1221 |
+
"grad_norm": 0.7410577535629272,
|
| 1222 |
+
"learning_rate": 3.4203113817116957e-05,
|
| 1223 |
+
"loss": 0.8418,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.1607565011820331,
|
| 1228 |
+
"grad_norm": 0.7604397535324097,
|
| 1229 |
+
"learning_rate": 3.272542485937369e-05,
|
| 1230 |
+
"loss": 1.1219,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.16170212765957448,
|
| 1235 |
+
"grad_norm": 0.6462581753730774,
|
| 1236 |
+
"learning_rate": 3.121724717912138e-05,
|
| 1237 |
+
"loss": 0.9533,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.16264775413711585,
|
| 1242 |
+
"grad_norm": 0.2718241810798645,
|
| 1243 |
+
"learning_rate": 2.9684532864643122e-05,
|
| 1244 |
+
"loss": 0.5001,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.1635933806146572,
|
| 1249 |
+
"grad_norm": 0.35057616233825684,
|
| 1250 |
+
"learning_rate": 2.8133330839107608e-05,
|
| 1251 |
+
"loss": 0.5601,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.16453900709219857,
|
| 1256 |
+
"grad_norm": 0.5394273996353149,
|
| 1257 |
+
"learning_rate": 2.656976298823284e-05,
|
| 1258 |
+
"loss": 0.8314,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.16548463356973994,
|
| 1263 |
+
"grad_norm": 0.3971342444419861,
|
| 1264 |
+
"learning_rate": 2.5e-05,
|
| 1265 |
+
"loss": 0.7177,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.16643026004728131,
|
| 1270 |
+
"grad_norm": 0.3941769003868103,
|
| 1271 |
+
"learning_rate": 2.3430237011767167e-05,
|
| 1272 |
+
"loss": 0.6324,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.1673758865248227,
|
| 1277 |
+
"grad_norm": 0.45238277316093445,
|
| 1278 |
+
"learning_rate": 2.186666916089239e-05,
|
| 1279 |
+
"loss": 0.7953,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.16832151300236406,
|
| 1284 |
+
"grad_norm": 0.5700445771217346,
|
| 1285 |
+
"learning_rate": 2.031546713535688e-05,
|
| 1286 |
+
"loss": 0.859,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.16926713947990543,
|
| 1291 |
+
"grad_norm": 0.47867706418037415,
|
| 1292 |
+
"learning_rate": 1.8782752820878634e-05,
|
| 1293 |
+
"loss": 0.8502,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.1702127659574468,
|
| 1298 |
+
"grad_norm": 0.42379331588745117,
|
| 1299 |
+
"learning_rate": 1.7274575140626318e-05,
|
| 1300 |
+
"loss": 0.8364,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.17115839243498818,
|
| 1305 |
+
"grad_norm": 0.4100590944290161,
|
| 1306 |
+
"learning_rate": 1.5796886182883053e-05,
|
| 1307 |
+
"loss": 0.7299,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.17210401891252955,
|
| 1312 |
+
"grad_norm": 0.5437663197517395,
|
| 1313 |
+
"learning_rate": 1.4355517710873184e-05,
|
| 1314 |
+
"loss": 0.7789,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.17304964539007092,
|
| 1319 |
+
"grad_norm": 0.47485315799713135,
|
| 1320 |
+
"learning_rate": 1.2956158147457115e-05,
|
| 1321 |
+
"loss": 0.8491,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.1739952718676123,
|
| 1326 |
+
"grad_norm": 0.48820245265960693,
|
| 1327 |
+
"learning_rate": 1.1604330125525079e-05,
|
| 1328 |
+
"loss": 0.926,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.17494089834515367,
|
| 1333 |
+
"grad_norm": 0.32581862807273865,
|
| 1334 |
+
"learning_rate": 1.0305368692688174e-05,
|
| 1335 |
+
"loss": 0.5398,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.17588652482269504,
|
| 1340 |
+
"grad_norm": 0.4086638391017914,
|
| 1341 |
+
"learning_rate": 9.064400256282757e-06,
|
| 1342 |
+
"loss": 0.8114,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.1768321513002364,
|
| 1347 |
+
"grad_norm": 0.4679095447063446,
|
| 1348 |
+
"learning_rate": 7.886322351782783e-06,
|
| 1349 |
+
"loss": 0.8871,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.17777777777777778,
|
| 1354 |
+
"grad_norm": 0.4896736145019531,
|
| 1355 |
+
"learning_rate": 6.775784314464717e-06,
|
| 1356 |
+
"loss": 0.81,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.17872340425531916,
|
| 1361 |
+
"grad_norm": 0.4382385015487671,
|
| 1362 |
+
"learning_rate": 5.737168930605272e-06,
|
| 1363 |
+
"loss": 0.8284,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.17966903073286053,
|
| 1368 |
+
"grad_norm": 0.5600558519363403,
|
| 1369 |
+
"learning_rate": 4.7745751406263165e-06,
|
| 1370 |
+
"loss": 1.0058,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.1806146572104019,
|
| 1375 |
+
"grad_norm": 0.5055614113807678,
|
| 1376 |
+
"learning_rate": 3.891801862449629e-06,
|
| 1377 |
+
"loss": 0.8065,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.18156028368794327,
|
| 1382 |
+
"grad_norm": 0.6402313113212585,
|
| 1383 |
+
"learning_rate": 3.092332998903416e-06,
|
| 1384 |
+
"loss": 1.0421,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.18250591016548465,
|
| 1389 |
+
"grad_norm": 0.5336678624153137,
|
| 1390 |
+
"learning_rate": 2.379323688349516e-06,
|
| 1391 |
+
"loss": 0.8897,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.183451536643026,
|
| 1396 |
+
"grad_norm": 0.5516868829727173,
|
| 1397 |
+
"learning_rate": 1.7555878527937164e-06,
|
| 1398 |
+
"loss": 0.8386,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.18439716312056736,
|
| 1403 |
+
"grad_norm": 0.6657341718673706,
|
| 1404 |
+
"learning_rate": 1.2235870926211619e-06,
|
| 1405 |
+
"loss": 1.1191,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.18534278959810874,
|
| 1410 |
+
"grad_norm": 0.5750419497489929,
|
| 1411 |
+
"learning_rate": 7.854209717842231e-07,
|
| 1412 |
+
"loss": 1.0913,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.1862884160756501,
|
| 1417 |
+
"grad_norm": 0.4884861409664154,
|
| 1418 |
+
"learning_rate": 4.4281873178278475e-07,
|
| 1419 |
+
"loss": 0.976,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.18723404255319148,
|
| 1424 |
+
"grad_norm": 0.5465104579925537,
|
| 1425 |
+
"learning_rate": 1.9713246713805588e-07,
|
| 1426 |
+
"loss": 0.8359,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.18817966903073285,
|
| 1431 |
+
"grad_norm": 0.6062586903572083,
|
| 1432 |
+
"learning_rate": 4.9331789293211026e-08,
|
| 1433 |
+
"loss": 0.9467,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.18912529550827423,
|
| 1438 |
+
"grad_norm": 0.7774025201797485,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.1784,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.18912529550827423,
|
| 1445 |
+
"eval_loss": 0.8490656018257141,
|
| 1446 |
+
"eval_runtime": 54.2258,
|
| 1447 |
+
"eval_samples_per_second": 65.707,
|
| 1448 |
+
"eval_steps_per_second": 16.431,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 1470 |
"should_evaluate": false,
|
| 1471 |
"should_log": false,
|
| 1472 |
"should_save": true,
|
| 1473 |
+
"should_training_stop": true
|
| 1474 |
},
|
| 1475 |
"attributes": {}
|
| 1476 |
}
|
| 1477 |
},
|
| 1478 |
+
"total_flos": 2.614235570896896e+16,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|